Low-Energy Architectures of Linear Classifiers for IoT Applications using Incremental Precision and Multi-Level Classification
Low-Energy Architectures of Linear Classifiers for IoT Applications using Incremental Precision and Multi-Level Classification
复制标题
使用增量精度和多级分类的物联网应用线性分类器的低能耗架构
DOI：
10.1145/3194554.3194603
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Parhi, Keshab K.
中科院分区：
文献类型：
--
作者：
Koteshwara, Sandhya;Parhi, Keshab K.
本文提出了一种新的增量精度分类方法，该方法可以减少物联网应用中线性分类器的能耗。特征首先被输入到低精度分类器。如果分类器成功地对样本进行分类，则过程终止。否则，通过使用更高精度的分类器来逐步改善分类性能。重复该过程，直到分类完成。其论点是，许多样本可以使用低精度分类器进行分类，从而减少能量。为了实现增量精度，提出了一种新的数据路径分解方法来设计固定宽度的加法器和乘法器。这些组件无需重新计算输出即可提高精度，从而降低能耗。使用线性分类的例子，它表明，所提出的增量精度为基础的多级分类器的方法可以减少约41%的能量，同时实现可比的准确性作为一个全精度系统。
This paper presents a novel incremental-precision classification approach that leads to a reduction in energy consumption of linear classifiers for IoT applications. Features are first input to a low-precision classifier. If the classifier successfully classifies the sample, then the process terminates. Otherwise, the classification performance is incrementally improved by using a classifier of higher precision. This process is repeated until the classification is complete. The argument is that many samples can be classified using the low-precision classifier, leading to a reduction in energy. To achieve incremental-precision, a novel data-path decomposition is proposed to design of fixed-width adders and multipliers. These components improve the precision without recalculating the outputs, thus reducing energy. Using a linear classification example, it is shown that the proposed incremental-precision based multi-level classifier approach can reduce energy by about 41% while achieving comparable accuracies as that of a full-precision system.
DOI：
--
发表时间：
1997
期刊：
J. VLSI Signal Process.
影响因子：
--
作者：
S. Nawab;A. Oppenheim;A. Chandrakasan;J. Winograd;J. T. Ludwig
通讯作者：
J. T. Ludwig